A pi extension that brings Claude Code-style autonomous sub-agents and workflow orchestration to pi, allowing for parallel background agents and scripted workflows.

An AI-powered game development assistant that connects AI agents to Unity via the Model Context Protocol to automate editor workflows and enable in-game AI behavior.

Lemonade is an open‑source local AI server that runs LLMs, speech, TTS, image and other multimodal models on your own CPU/GPU/NPU. It provides a standard OpenAI‑compatible HTTP API, a CLI for model management, and two distribution flavors – a full server service and a portable embeddable binary. Supports Windows, macOS, Linux (many distros, Docker, Snap) and a broad set of hardware back‑ends (CUDA, ROCm, Vulkan, Metal, AMD NPU, etc.).

A coding agent that runs in the terminal, optimized for low-cost models and capable of executing local commands and operating computer interfaces.

A set of custom ComfyUI nodes for webcam/screen capture, region‑mask creation, OpenPose editing, video trimming/concatenation, and a MiniMax‑H3 prompt builder, enabling richer image‑and‑video generation workflows.

A collection of reusable skill modules and instructions that AI agents can load to execute specific workflows like research, coding orchestration, and system operations.

A high-performance copy-paste detector for source code that identifies duplicated blocks across 224+ languages to help developers and AI agents refactor code.

An open-source observability platform built on OpenTelemetry that unifies logs, metrics, and traces to monitor applications, infrastructure, and AI/LLM pipelines.

A native x64dbg plugin that exposes the debugger's full functionality to AI agents via the Model Context Protocol (MCP), enabling agentic reverse engineering.

A Claude Code skill suite that automates the full blog lifecycle, using a 5-gate delivery contract to ensure high-quality, SEO-optimized, and AI-citation-ready content.

DeepWiki-Open is an automated tool that analyzes code repositories to generate interactive wikis, visual diagrams, and guided codemaps for documentation.

An open-source AI memory system that captures screen and audio data from wearables and desktop apps to provide real-time transcription, summaries, and a searchable AI chat.

A lightweight, GPU-accelerated framework for robot learning that combines Isaac Lab's manager-based API with MuJoCo Warp.

Skyvern is an open‑source platform that adds LLM‑driven, vision‑based automation to Playwright. It lets developers and non‑technical users control browsers with natural‑language prompts, build reusable workflows, and run either locally (pip or Docker) or via a managed cloud service.

ExploitGym is a large-scale benchmark of real-world vulnerabilities used to evaluate the ability of AI agents to develop functional security exploits.

An open-source platform for building enterprise-grade AI agents that integrates RAG pipelines and agentic workflows to create intelligent knowledge bases and customer service tools.

A virtual filesystem and execution environment hosted in Cloudflare Durable Objects, allowing code and shell commands to run across containers or Worker isolates with persistent state.

An open-source AI-native vector design tool that generates UI layouts from natural language prompts and exports them to production code.

A complete from-scratch PyTorch implementation of an LLM pipeline, covering everything from raw text tokenization and Transformer architecture to SFT and advanced RLHF alignment techniques like PPO and GRPO.

OpenOutreach is a self‑hosted CLI that uses an LLM and a licensed lead‑data service to discover, qualify, and email B2B prospects based on a simple product description. It bundles two child tools—OpenOutFind (search & qualification) and OpenOutSend (email enrichment & sending)—into a one‑command workflow, requires only an LLM key, a BetterContact API key, and SMTP credentials, and outputs ready‑to‑import CSV files with a human‑readable reason for each lead.

A KVCache-centric disaggregated architecture for LLM serving that optimizes data movement and storage to increase request handling and reduce latency.

A lightweight, dependency-free C/C++ tensor library for machine learning designed for high efficiency and cross-platform portability.

A high-performance web scraping and crawling engine that converts URLs into clean markdown or structured JSON for AI agents and RAG pipelines.

An open-source web control panel and engineering toolkit for managing Quectel cellular modems, featuring eSIM management, WiFi Calling, and SMS orchestration.

A comprehensive learning resource and kernel library for modern CUDA programming with PyTorch, featuring over 200 kernels ranging from basic operations to high-performance FlashAttention and HGEMM implementations.

An autonomous penetration testing agent that uses LLMs to drive a Kali Linux sandbox and Caido proxy through a structured recon-to-report pipeline.

Figwright is a free, locally‑run MCP server + Figma plugin that lets AI agents read from and write to Figma files. It provides 113 bidirectional tools (inspection, export, creation, editing, grounding) and two ready‑made agent skills (codegen and build). The whole stack runs on your machine, works with the free Figma tier, and is extensible via custom skills.

An MCP server for searching and downloading academic papers from multiple open-access and public sources, designed for LLM-enhanced research workflows.

An AI-powered penetration testing framework that automates reconnaissance and exploitation using an attack-graph-driven self-evolving loop to find verified vulnerabilities.

A unified agent sandbox environment that combines a browser, shell, and IDE tools in one Docker container with a shared filesystem for AI agents.

A Vulkan-based frame generation and spatial scaling tool for SteamOS and Linux gaming that integrates with Lossless Scaling models to improve FPS and visual quality.

An open-source dependency manager for AI agents that allows developers to declare and share agent configurations, skills, and plugins via a portable manifest file.

An agent-led job application workflow and local tracking dashboard that uses AI coding agents to automate job searching and form-filling with strict human-in-the-loop safety boundaries.

An open agent framework that provides AI agents with a Dockerized Linux desktop and browser, enabling them to use real GUI software and collaborate on live documents.

PyRIT is an open-source framework that enables security professionals and engineers to proactively identify risks in generative AI systems.

A context engineering layer for AI coding agents that compresses inputs and shell outputs to reduce token costs and extend context windows.

Model Context Protocol (MCP) is an open standard that provides a universal way for AI models to connect to data sources and tools, reducing the need for custom integrations.

An open-source browser extension that transforms the DeepSeek web interface into an AI agent workspace with long-term memory, MCP tool integration, and browser automation.

A collection of 157 AI agent skills providing specialized e-commerce expertise for sellers on Amazon, Shopify, eBay, and other major platforms.

The OpenAI Agents SDK (JavaScript/TypeScript) lets developers create text, sandbox, and realtime agents that can call LLMs, use tools, enforce guardrails, hand off work, and track runs. It runs in Node.js, Deno, Bun, and experimentally in Cloudflare Workers.

A decision engine and orchestration framework for spec-driven AI development that ensures software stability by requiring human-led decisions before AI agents execute tasks.

A kernel extension for macOS 27 that spoofs the device region code from CH/A to LL/A to enable Apple Intelligence on mainland China Mac hardware.

An AI coding agent that builds software and continuously learns a developer's specific coding style and preferences through a taste profile.

An open-source, deterministic browser automation platform for building visual scraping and automation workflows that can be triggered via API.

A Kubernetes-native framework for building, deploying, and managing AI agents as declarative custom resources.

NeMo AutoModel is a Python library from NVIDIA that provides ready‑to‑use, highly‑optimized training recipes for a huge range of LLMs, VLMs, and diffusion models. It supports full‑parameter and LoRA fine‑tuning, multi‑node tensor‑ and pipeline‑parallelism, and even speculative‑decoding drafters, all driven by simple YAML configs.

Chroma is an open-source vector database for AI that simplifies the storage, retrieval, and indexing of embeddings for similarity search.

A computational research tool for serial-section histology and proteomic image analysis, enabling 3D reconstruction and spatial topology profiling across tissue sections.